Research map / 3D vision / Gaussian splatting
Augmented Radiance Field: A General Framework for Enhanced Gaussian Splatting
Yixin Yang, Bojian Wu, Yang Zhou, Hui Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add view-dependent-opacity supplementary Gaussians (augmentation) to 3DGS-MCMC | 3DGS-MCMC · Mip-NeRF 360 | PSNR: 28.29 -> 28.96 | Improved |
| add supplementary Gaussians to 3DGS (sh=3) | 3DGS · Mip-NeRF 360 | PSNR: 27.21 -> 28.39 | Improved |
| add the view-dependent opacity lobe to supplementary Gaussians (ablation) | augmented 3DGS-MCMC · Mip-NeRF 360 | PSNR: 28.45 -> 28.96 | Improved |
| add extra Gaussians without opacity lobe (ablation) | 3DGS-MCMC · Mip-NeRF 360 | PSNR: 28.33 -> 28.45 | Improved |
| optimize lobe span T instead of fixing T=0.5 (ablation) | augmented 3DGS-MCMC · Mip-NeRF 360 | PSNR: 28.60 -> 28.96 | Improved |
| optimize lobe sharpness beta instead of fixing beta=0 (ablation) | augmented 3DGS-MCMC · Mip-NeRF 360 | PSNR: 28.93 -> 28.96 | Improved |
| vary supplementary Gaussian ratio (5%, 10%, 15%) (ablation) | augmented 3DGS-MCMC · Mip-NeRF 360 and Tanks&Temples | PSNR: 5%: 28.88; 10%: 28.96; 15%: 28.94 (Mip-NeRF 360) | No clear effect |
| raise SH order from 3 to 4 in 3DGS (ablation) | 3DGS · Mip-NeRF 360 | PSNR: 27.47 -> 27.55 (memory 608 -> 887 MB) | No clear effect |
| use second-order SH instead of third-order SH in augmented MCMC (ablation) | Ours (MCMC) · Mip-NeRF 360 | PSNR: 28.96 -> 28.89 | No clear effect |
| use opacity-lobe Gaussians instead of Spherical Beta (DBS) on shiny synthetic data | Ours (MCMC, sh=3) · Synthetic shiny dataset (glossy) | PSNR: 41.70 -> 42.33 | Improved |
| use opacity-lobe Gaussians instead of Spherical Beta (DBS) on NeRF Synthetic | Ours (MCMC, sh=3) · NeRF Synthetic | PSNR: 34.64 -> 34.35 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Zip-NeRF — Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields (ICCV 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.93)
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.93)
- Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.92)
- 3D-HGS: 3D Half-Gaussian Splatting (CVPR 2025 · similarity 0.92)
- 6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering (ICLR 2025 · similarity 0.92)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.92)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
